Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 757 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.5446. Min Range: -0.5446

Max Act: 0.5446. Min Act: 0.0000

Data Index: 194574 (C4 (Web Text))

Max Activating Token Index: 396

Text #1

Max Range: 0.5446. Min Range: -0.5446

Max Act: 0.4928. Min Act: 0.0000

Data Index: 410195 (C4 (Web Text))

Max Activating Token Index: 128

Text #2

Max Range: 0.5446. Min Range: -0.5446

Max Act: 0.5231. Min Act: -0.0000

Data Index: 1133307 (C4 (Web Text))

Max Activating Token Index: 749

Text #3

Max Range: 0.5446. Min Range: -0.5446

Max Act: 0.4782. Min Act: 0.0000

Data Index: 980765 (C4 (Web Text))

Max Activating Token Index: 226

Text #4

Max Range: 0.5446. Min Range: -0.5446

Max Act: 0.4566. Min Act: -0.0000

Data Index: 112553 (C4 (Web Text))

Max Activating Token Index: 276

Text #5

Max Range: 0.5446. Min Range: -0.5446

Max Act: 0.4177. Min Act: -0.0000

Data Index: 1050356 (C4 (Web Text))

Max Activating Token Index: 439

Text #6

Max Range: 0.5446. Min Range: -0.5446

Max Act: 0.4332. Min Act: 0.0000

Data Index: 172453 (C4 (Web Text))

Max Activating Token Index: 473

Text #7

Max Range: 0.5446. Min Range: -0.5446

Max Act: 0.4153. Min Act: 0.0000

Data Index: 1059887 (C4 (Web Text))

Max Activating Token Index: 803

Text #8

Max Range: 0.5446. Min Range: -0.5446

Max Act: 0.4139. Min Act: 0.0000

Data Index: 1039847 (C4 (Web Text))

Max Activating Token Index: 331

Text #9

Max Range: 0.5446. Min Range: -0.5446

Max Act: 0.4039. Min Act: 0.0000

Data Index: 741782 (C4 (Web Text))

Max Activating Token Index: 903

Text #10

Max Range: 0.5446. Min Range: -0.5446

Max Act: 0.3825. Min Act: -0.0000

Data Index: 753174 (C4 (Web Text))

Max Activating Token Index: 1000

Text #11

Max Range: 0.5446. Min Range: -0.5446

Max Act: 0.4026. Min Act: -0.0000

Data Index: 53675 (C4 (Web Text))

Max Activating Token Index: 711

Text #12

Max Range: 0.5446. Min Range: -0.5446

Max Act: 0.4138. Min Act: -0.0000

Data Index: 477564 (C4 (Web Text))

Max Activating Token Index: 867

Text #13

Max Range: 0.5446. Min Range: -0.5446

Max Act: 0.4049. Min Act: -0.0000

Data Index: 1337904 (C4 (Web Text))

Max Activating Token Index: 367

Text #14

Max Range: 0.5446. Min Range: -0.5446

Max Act: 0.3884. Min Act: -0.0000

Data Index: 245466 (C4 (Web Text))

Max Activating Token Index: 409

Text #15

Max Range: 0.5446. Min Range: -0.5446

Max Act: 0.3804. Min Act: -0.0000

Data Index: 257731 (C4 (Web Text))

Max Activating Token Index: 640

Text #16

Max Range: 0.5446. Min Range: -0.5446

Max Act: 0.3695. Min Act: -0.0000

Data Index: 1324371 (C4 (Web Text))

Max Activating Token Index: 485

Text #17

Max Range: 0.5446. Min Range: -0.5446

Max Act: 0.3773. Min Act: -0.0000

Data Index: 67567 (C4 (Web Text))

Max Activating Token Index: 521

Text #18

Max Range: 0.5446. Min Range: -0.5446

Max Act: 0.3865. Min Act: -0.0000

Data Index: 925768 (C4 (Web Text))

Max Activating Token Index: 489

Text #19

Max Range: 0.5446. Min Range: -0.5446

Max Act: 0.3858. Min Act: -0.0000

Data Index: 230273 (C4 (Web Text))

Max Activating Token Index: 842